dsh-cherry-provider-bridge
Run the following command in DeepSeek Harness:
dsh plugin install LiweiDonVee/dsh-cherry-provider-bridge
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install LiweiDonVee/dsh-cherry-provider-bridge in DeepSeek Harness to install the plugin; source code is available at https://github.com/LiweiDonVee/dsh-cherry-provider-bridge
About this plugin
You have already configured a provider in Cherry Studio—API key, endpoint, model catalog—and you want to reuse that exact setup inside DeepSeek Harness without re-typing a single character. dsh-cherry-provider-bridge does one job and does it cleanly: it opens Cherry Studio's SQLite database in read-only mode, extracts the credential and model route for the one provider you select, and writes them into DSH's credential store and route table. There is no GET /models discovery call, and the database file never leaves your machine.
The sync loop runs every five seconds, skips values that have not changed, and retries automatically on transient lock or namespace errors. It appends a missing /v1 path segment once, preserves model metadata and compatible reasoning options, and strictly limits its writes to the single provider you name. Data ownership stays with you: uninstalling the plugin stops synchronization but leaves the copied key and route in DSH—remove them manually through DSH if you want a clean slate.
This bridge is aimed at developers who manage providers through Cherry Studio and invoke them via DeepSeek Harness, and would rather not copy API keys and model lists between two toolsets by hand. It is an independent community adapter, not an official Cherry Studio plugin, not a fork of Cherry Studio, and not affiliated with DeepSeek AI. Released under the MIT license.
Use Cases
- Reuse a fully configured Cherry Studio provider in DeepSeek Harness without manually copying keys or endpoints
- Skip GET /models discovery by registering routes from local SQLite data alone, reducing dependency on external APIs
- Switch or verify models across multiple providers while preserving original metadata and reasoning options without losing fields
Best For
- Developers who manage providers in Cherry Studio and invoke them through DeepSeek Harness
- Ops or research engineers who want to avoid pasting API keys and model lists between two toolsets manually
- Privacy-sensitive users who insist credentials and model data never transit through an external service
Related Plugins
Free web search plugin for DeepSeek Harness with web search, X search, and page fetch; no signup or API key required, with automatic multi-engine failover.
AnySearch-powered web and vertical search plugin for DeepSeek Harness, offering real-time search, cleaned URL content, concurrent batch search via native web_search/web_fetch, no API key required.
Pixel-perfect webpage clone tool that uses an agent harness to turn any webpage into a scored, full-page React replica.
A bilingual cost-tracking plugin for DeepSeek Harness with session/daily cost, budget, official & custom provider balance, coding plan quotas, peak/off-peak pricing alerts, and history stats.